GitHub - zha0/lit-llama at 3ba48f674ac0b76c58bacb9c143ea53d457a8983

zha0 / lit-llama Public

forked from Lightning-AI/lit-llama

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Apache-2.0 license

0 stars 518 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 29 Commits
.github		.github
quantization		quantization
scripts		scripts
.gitignore		.gitignore
.pre-commit-config.yaml		.pre-commit-config.yaml
LICENSE		LICENSE
README.md		README.md
generate.py		generate.py
model.py		model.py
pyproject.toml		pyproject.toml
requirements.txt		requirements.txt
tokenizer.py		tokenizer.py
train.py		train.py

Repository files navigation

About

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Activity

Report repository